Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to invisibility and hidden aspects of identity or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uts
    -0.15
     handleClick
    -0.14
    ilda
    -0.14
     laz
    -0.13
    дап
    -0.13
     Laz
    -0.13
    onu
    -0.13
     intolerance
    -0.12
    Handling
    -0.12
    Łèĥ½
    -0.12
    POSITIVE LOGITS
     hidden
    0.66
     hiding
    0.59
    -hidden
    0.59
    éļIJèĹı
    0.57
    hidden
    0.56
     secret
    0.56
     concealed
    0.54
     hid
    0.54
     Hidden
    0.54
    Hidden
    0.52
    Act Density 0.776%

    No Known Activations